github Python analyzed d67c059

zenml-io/mcp-zenml

github

MCP server to connect an MCP client (Cursor, Claude Desktop etc) with your ZenML MLOps and LLMOps pipelines

maintainer
zenml-io
license
MIT
first seen
2026-05-22
last seen
2026-07-15
releases · 30d
0
short id
risk 67/100 · heuristic grade
D high
  • capability exposure inferred + 35
  • recent drift inferred + 20
  • tool safety inferred + 17
  • trust mitigators mixed − 5

inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 4m ago · see ecosystem CVEs →

risk trajectory 8 movements
  • C · 59 D · 67
  • B · 23 C · 59
  • B · 25 B · 23
  • B · 27 B · 25
  • B · 23 B · 27
  • B · 28 B · 23
  • C · 38 B · 28
  • C · 35 C · 38
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 3 findings · grade factor +17
  1. high dangerous code

    dynamic exec: pickle.loads(), eval()/exec(), __import__()

  2. medium toxic flow (lethal trifecta)

    lethal trifecta reachable across this server's tool + source surface: private-data access + untrusted-content ingestion + network exfil (a leg is proven only in the analyzed source)

  3. low dangerous code

    env-secret-flows-to-network-py: An environment value (often a secret/token) flows into a network call — possible credential exfiltration. (/scratch/obs-code-vJlGTw/zenml-io-mcp-zen

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit d67c059 · analyzer v28 · 4d ago

skills & prompt files 11

danger signals33

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/mcpso:zenml-io/mcp-zenml/badge.svg)](https://mcpobservatory.com/servers/mcpso:zenml-io/mcp-zenml/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of zenml-io.